@backnotprop
github is the fun stuff. day to day is complex critical systems, mostly involving AI.
73 skills3 repositories 12.1K
Turn implementation plans, pull request changes, and technical concepts into HTML visual explanations with Plannotator styling. Present diagrams, mockups, and review priorities through an annotation interface, with approval controls for plans and proposals.
Audit npm dependencies before updating them with Bun. Check maintainers, release age, signatures, published file changes, and release notes, then update packages that pass review and record deferred updates for later follow-up.
Review code changes in Plannotator’s browser interface and have the agent address returned comments. Choose the current working directory, another checkout, or a pull or merge request URL, with options to focus on a specific comparison base.
Open the assistant’s latest rendered message in Plannotator and return specific annotations for revision. The skill distinguishes requested edits from approval, approval with notes, and a closed session, so each review result receives the appropriate response.
Prepare and publish a Plannotator release with contributor credits, coordinated version updates, ordered builds, and tag-triggered publishing. The workflow also checks package contents, security scan results, and evidence showing how release files were built.
Turn an idea into a goal package for /goal. Collect decisions through Plannotator, review testable requirements, explore the codebase, and produce an approved execution plan with verification steps and a clear completion condition.
Review Markdown files, HTML files, URLs, or folders in Plannotator’s annotation interface. The agent responds to requested changes and distinguishes them from approvals, optional approval notes, and sessions closed without feedback.
Open documents, text configuration files, HTML, URLs, or folders in Plannotator for browser review. The agent responds to returned annotations and can use an approval session when you need to accept a plan, specification, or document.
Use Plannotator to review plans, code changes, documents, and running local apps in a browser. This reference covers returning feedback to agents, browsing past decisions, sharing guided code reviews, and leaving questions for later replies.
Analyze rejected plans and reviewer feedback to identify recurring concerns, changing expectations, and concrete prompt improvements. Produce an HTML dashboard from Plannotator archives, or use Claude Code plan rejection reasons when those archives are unavailable.
Open Plannotator’s browser-based code review interface from Kiro and address the returned feedback. Review the current directory, another working directory, or a pull request URL, and optionally choose a comparison base to focus the changes shown.
Open files, folders, or URLs in Plannotator’s annotation interface, then have the agent address the returned comments. Use it to review Markdown, plain-text configuration files, or HTML through a shared feedback workflow.
Review Renovate pull requests that update GitHub Actions. Verify pinned commits against upstream version tags, inspect release notes for breaking changes, and check existing workflow settings before giving a clear recommendation on whether to merge.
Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, "is the model still true to the code", or after merges and refactors that touched verified code without rechecking it.
The English summary is being prepared. Showing the original description.
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, "model-check this race", "prove this invariant", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.
The English summary is being prepared. Showing the original description.
Sharpen a task before starting: the expert approach, what the user is really after, and the right level of specification. Use for /sharpen.
The English summary is being prepared. Showing the original description.
Restate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words.
The English summary is being prepared. Showing the original description.
Configure Benny and prepare its triage and repro automations. Use when installing Benny or changing its Slack, tracker, repository, routing, control, model, or budget settings.
The English summary is being prepared. Showing the original description.
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
The English summary is being prepared. Showing the original description.
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
The English summary is being prepared. Showing the original description.
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
The English summary is being prepared. Showing the original description.
Cut AI tells from any writing.
The English summary is being prepared. Showing the original description.
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
The English summary is being prepared. Showing the original description.
Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)